© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 39092
    Prev
    Next
    INDEX
    Explanations

    this case, this law

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron flags any form of the Russian stem “данн” (e.g. данные, данный, данном, данных) referring to “data” or “given.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ’
    -2.33
    嶮
    -1.96
    Läh
    -1.93
     vekt
    -1.92
    푢
    -1.79
    狆
    -1.76
    卺
    -1.74
     Kı
    -1.73
    我们的
    -1.73
     exemple
    -1.72
    POSITIVE LOGITS
    of
    2.28
    S
    2.27
    1
    2.11
     inscrição
    2.05
    ).
    2.05
    不久
    2.03
    诹
    1.93
    inafter
    1.91
    鸨
    1.83
    </em>
    1.81
    Activations Density 0.004%

    No Known Activations